BesiegeField - Catapult - Single-agent: leaderboard
Metric: Mean distance (m). Source: besiegefield.github.io. Saturation forecast: Not forecast. 8 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | DeepSeek V3 | 3.5 |
| 2 | Llama 4 Scout | 3.18 |
| 3 | O3 | 2.87 |
| 4 | Gemini 2.5 Pro | 2.3 |
| 5 | Qwen 3 Coder 480B A35B | 1.75 |
| 6 | Claude Opus 4 (20250514) | 1.19 |
Interactive version: theaggregate.ai/benchmark?slug=besiegefield-catapult-single-agent · How It Works · Data refreshed daily, snapshot 2026-10-09.